From the Sector

Over the past three years, a dedicated AI development team at BTMA member Shelton Vision has been developing tailored machine learning solutions for the textiles industry.

The aim has been to elevate the detection process and the accuracy of naming and grading subtle defects in textiles, in real time within production environments.

“Big Data ‘off-the-shelf’ systems such as those behind technolgies like facial recognition and Google Maps involve reading many thousands of single images each second and simply take too long to accumulate sufficient data for what’s required in this specific case,” says Shelton Vision CEO and Managing Director Mark Shelton. “A feature of the textile industry is that in many sectors, the product range changes several times within a year and it is not uncommon to have to inspect hundreds, if not thousands of different styles in a year based on precise settings.”

In terms of defect types, he adds, there may typically be over 100 that need to be accurately detected, classified (named) and graded in real time.

“Added to this is the need to ‘filter out’ the random occurrence of ‘non defects’, such as loose threads, lint and dust on the surface – the number of which can be higher than actual defects – and it is clear that a bespoke system is required.”
The development team has consequently established metadata for identifying defect properties, enabling the successful identification of faults from a much smaller number of images.

“The system employs a unique combination of machine learning for automated style training and novel algorithms for defect detection, to provide high quality images for the AI real time defect classification and grading software,” Shelton explains. “Due to the inherent variation in fabric features – raw materials, construction, texture, colour and finishes, as well as the differing product quality standards in value chains and the regional variations in what defects are called – our AI engine uses models built for each individual company or group of companies, or product value chain.”

The AI models are constructed so that the user operatives can populate them with their own data produced by the vision system or by obtaining defect images from another imaging source (eg a mobile phone camera).  

The occurrence of defects is sporadic and many defect types occur infrequently, although when they do, they can have severe consequences. These scenarios re-enforce the need for the AI engine to be quickly set up and able to operate accurately with limited data sets of typically between 30 and 50 good quality images per defect type.

A further feature is a tool enabling the user to periodically ‘clean up’ the AI data during the set up phase. This is used to resolve conflicting data and to correct mis-named images.

Generally, the highest cost component of fabric production is the raw material and in addition to finished product inspection, a cost effective use for vision systems is in process operation.

Generally, the highest cost component of fabric production is the raw material and in addition to finished product inspection, a cost effective use for vision systems is in process operation.

“There is a need for the real time detection of defects that are being created in separate processes, such as printing or coating and for real time automated systems that can accurately determine the defects and their severity and provide a reliable signal for an operative to rectify the issue, This can result in considerable savings.

Prior to Shelton introducing powerful customised machine vision and real time defect classification, the only systems available were those that required manual sifting through vast numbers of images, which included both real defects and ‘non defect’ images. The task was very often overwhelming and did not provide much benefit beyond manual fabric inspection.

Many people across the world are bedridden – be it due to illness, an accident or old age. Because those affected often cannot move or turn over by themselves, they often end up with very painful bedsores. In the future, it should be possible to avoid bedsores with the help of materials that can be programmed to entirely adapt their form and mechanical properties. For example, the body support of mattresses made from programmable materials can be adjusted in any given area at the push of a button. Furthermore, the support layer is formed in such a way that strong pressure on one point can be distributed across a wider area. Areas of the bed where pressure is placed are automatically made softer and more elastic. Caregivers can also adjust the ergonomic lying position to best fit their patient.

Materials and microstructuring
Materials for applications requiring specific changes to stiffness or shape are being developed by researchers from Fraunhofer CPM, which is formed of six core institutes with the aim of designing and producing programmable materials. So, how can we program materials? “Essentially, there are two key areas where adjustments can be made: the base material – thermoplastic polymers in the case of mattresses and metallic alloys for other applications, including shape memory alloys – and, more specifically, the microstructure,” explains Dr. Heiko Andrä, spokesperson on the topic at the Fraunhofer Institute for Industrial Mathematics ITWM, one of the Fraunhofer CPM core institutes. “The microstructure of these metamaterials is made up of unit cells that consist of structural elements such as small beams and thin shells.” While the size of each unit cell and its structural elements in conventional cellular materials, like foams, vary randomly, the cells in the programmable materials are also variable – but can be precisely defined, i.e., programmed. This programming can be made, for example, in such a way that pressure on a particular position will result in specific changes at other regions of the mattress, i.e., increase the size of the contact surface and provide optimal support to certain areas of the body.

Materials can also react to temperature or humidity
The change in shape that the material should exhibit and the stimuli to which it reacts - mechanical stress, heat, moisture or even an electric or magnetic field - can be determined by the choice of material and its microstructure.

The journey to application
A single piece of material can take the place of entire systems of sensors, regulators and actuators. The goal of Fraunhofer CPM is to reduce the complexity of systems by integrating their functionalities into the material and reducing material diversity. We always have industrial products in mind when developing the programmable materials. As such, we take mass production processes and material fatigue into account, among other things,” says Franziska Wenz, deputy spokesperson on the topic at the Fraunhofer Institute for Mechanics of Materials IWM, another core institute of Fraunhofer CPM. The initial pilot projects with industry partners are also already underway. The research team expects that initially, programmable materials will act as replacements for components in existing systems or be used in special applications such as medical mattresses, comfortable chairs, variable damping shoe soles and protective clothing. “Gradually, the proportion of programmable materials used will increase,” says Andrä. Ultimately, they can be used everywhere – from medicine and sporting goods to soft robotics and even space research.

January, 3rd, ZDHC announced the release of the updated ZDHC Man-Made Cellulosic Fibres (MMCF) Guidelines Version 2.0, and its supporting document. By publishing these documents the industry shall be pushed forward increasingly innovative and sustainable fibre production.

The ZDHC MMCF Guidelines V2.0 now include the Responsible Fibre Production Guidelines, Wastewater Guidelines and Air Emissions Guidelines as three separate chapters in a single document.

Fibres are key components of production processes in the textile and fashion value chain and it is crucial to reduce the environmental impact of their manufacture. ZDHC guidelines give suppliers producing MMCF unified criteria for measuring output indicators like wastewater, sludge, air emissions and other process-related parameters.

Among other changes, this update reflects the expansion of the scope to accommodate Viscose Filament Yarn, Lyocell, Cuprammonium Rayon (Cupro) and Cellulose Acetate (Acetate). The ZDHC Man-Made Cellulosic Fibres (MMCF) Guidelines V2.0 provide an aligned approach for included fibres, including defined chemical recovery, wastewater and sludge discharge, and air emission discharge.

ZDHC continues to advocate for the improvement of processes which minimise emissions while also working towards the recovery of input substances and by-products. These dual goals, reduction and recovery, directly address the negative impact of outputs arising from MMCF production.

ZDHC MMCF Guidelines Industry Standard Implementation Approach Version 2.0: Additional Industry Support for Implementation
Along with the ZDHC Man-Made Cellulosic Fibres (MMCF) Guidelines V2.0, ZDHC has also updated its ZDHC MMCF Guidelines Industry Standard Implementation Approach. This document aims to support the implementation process of the ZDHC MMCF Guidelines V2.0, and features new implementation timelines that assist suppliers in setting their goals to achieve Foundational, Progressive or Aspirational Level on the ZDHC Supplier Platform.

Toray Industries, Inc., announced that it has combined nanotechnology and fiber technology to create a cross-shaped polymethyl methacrylate (PMMA) nanopore fiber that efficiently adsorbs pathogenic proteins in the blood.

The company developed this fiber by employing its PMMA hollow fiber membrane spinning technology. Changing the nanopore size on the surface and inside the fiber makes it possible to control the types of protein that this material adsorbs. This could become a fundamental blood purification technology for a range of protein adsorption columns that cause diseases.

The fiber’s cross-shaped cross section has a larger surface area than fibers with round ones. This provides much better contact between the blood and fiber and significantly enhances protein adsorption efficiency.

Toray is the only company to have commercialized a PMMA hollow-fiber membrane artificial kidney for dialysis treatment. Its new nanopore fiber benefits from PMMA’s good protein adsorption and biocompatibility. Using the structural formation of a stereocomplex from two PMMA types entangled spirally during the spinning process to form the fiber shape, Toray made it possible for the fiber itself to develop pores of several to dozens of nanometers. Depending on the pore size, large proteins cannot go inside the pores. If they are too small, they are not trapped. This enables selective adsorption of moderately sized proteins trapped in pores.

The fiber pore sizes are adjustable to the diameters of target proteins for a range of diseases. These include inflammatory proteins in sepsis, autoantibodies in autoimmune diseases, and causative proteins in chronic illnesses. Toray’s technology is thus fundamental to developing disease-causing protein adsorption columns to purify blood.

Toray’s cross-shaped cross section suppresses inter-fiber adhesion, increasing the surface area per volume and enabling highly efficient protein adsorption. For blood purification applications, higher capacity adsorption columns increase blood removal amounts from the body, which can be especially stressful for the elderly and children. The new fiber’s highly efficient protein adsorption should contribute to compact, high-performance protein adsorption columns.

Textile companies could take full advantage of expanded print opportunities with EFI™ Reggiani textile solutions presented at the 8-13 December India ITME Exhibition in Greater Noida.

The EFI Reggiani TERRA Silver printer was shown at ITME 2022: a solution to enter the industrial printing segment with a short, smart and green process. The EFI Reggiani TERRA Solution eliminates the need for steaming or washing on direct-to-textile applications, using a greener, more efficient polymerisation process that takes place as the printed textile goes through the printer’s on-board dryer. As a result, users can achieve superior printing results while using less time, water, and energy.

The EFI Reggiani exhibit at ITME was also promoting:

•  EFI Reggiani HYPER printer, a scanning printer available in 1.8-metre, 2.4-metre or 3.4-metre widths that prints at up to 20 linear metres per minute peak speed, making it the fastest textile scanning printer on the market;
• Mezzera Concord, the continuous rope washing line from the specialist in washing solutions that transports fabric by overflow for tensionless running with an independent squeezing mangle for each channel;
• One of the industry’s broadest line-ups of high-end, superior-quality textile inks, including EFI Reggiani AQUA and EFI Reggiani Diamond reactive, IRIS dye-sublimation, ARIA direct disperse, FUOCO acid, and GEA and TERRA pigment inks; and
• Inèdit, recently acquired by EFI Reggiani, a developer of raster image processors (RIPs) and related software for digital industrial textile printing with their product portfolio that features proven, highly advanced workflow solutions for textile profiling, calibration, design integration and much more.

With the aim of increasing the use of post-consumer fibers in textiles, TEXAID launches a white tote bag. The fabric is a mixture of 50% used textile waste collected by TEXAID in Switzerland and Germany. At TEXAID's largest sorting facility in Apolda, Germany, white cotton textiles that can no longer be worn were sorted out and later spun, woven, and manufactured in Italy. Plastic waste makes up the other 50%. Unifi rescued this ocean-bound plastic waste and recycled it into fiber.

The cotton material was transformed into a fiber by Marchi & Fildi in Biella, IT, which was then spun into a yarn using recycled cotton and recycled polyester fibers. This yarn was woven into textile by Tessitura Casoni.T.F.C.. The care label and flag label were produced by the German company Bornemann-Etiketten GmbH, and an NFC chip from circular.fashion was also integrated into the product. All components were then assembled into this bag in Tuscany by benefit company Alisea Srl Società Benefit with their partner Paimex SRL and also screen printed with our design on it.

This NFC chip is a circularity.IDⓇ digital product passport, developed by the Berlin-based company, circular.fashion. By scanning the NFC chip on the bag with a cell phone, customers are redirected to the circularity.IDⓇ product platform. On this platform, they can find further information on the supply chain as well as instructions on how to refurbish or return the bag for proper recycling. Through this digital product passport, a total transparency over the entire bag production is enabled and for customers it is an easy and quick way to get the information they need.

The chip also allows the manual sorters to getthe product information much faster to make a better sorting decision, e.g. the fiber composition. For this purpose, circular.fashion's intelligent sorting stations are used to scan the chip. Several of these stations have been installed at TEXAID's sorting facility in Apolda, Germany, to facilitate optimized reuse and recycling decisions and ensure another life for the product or fiber.

On Monday, December 19 2022, the European energy ministers reached an agreement on a price cap for natural gas wholesale prices.

Despite welcoming the adoption of the instrument and the prospect to limit gas price speculations on the stock market, EURATEX considers the cap at 180 €/MWh to be still too high. Also, the complexity of the conditionalities triggering the cap may weaken its effectiveness and implementation: according to the legal proposal, the price level must be reached for three working days and European wholesale gas prices must remain, for the same length of time, at €35 above the global price of liquefied natural gas. Therefore, EURATEX urges the Council of the EU to improve this market correction mechanism.

Furthermore, EURATEX insists on the need to provide the industry with support measures to counteract competition from the US and other countries. Dirk Vantyghem, Director General of EURATEX, affirms: “The Industry is at the heart of the European way of life and the fundament of our social market economy. The European textile industry is 99.8% composed of SMEs, which struggle with tight margins while being at the upstream part of the supply chain: the EU must do more to save its industrial structure, its competitiveness and its capacity to provide essential products to European citizens”.

Mey GmbH & Co. KG, a global manufacturer of underwear, nightwear and lingerie based in Germany, is launching the world’s first men’s nightwear with CELLIANT® Viscose, which converts body heat into infrared energy.

Called mey Zzzleepwear - THE NEW SLEEP-LIFE BALANCE, the collection follows the successful debut of the similarly named women’s collection in 2021. It consists of four designs in Indigo available in T-shirts, short pants, long-sleeved shirts and long pants. CELLIANT works by recycling the heat emitted by the body into full-spectrum infrared energy and then returns it to the body. As a result, it increases the supply of oxygen to the cells and promotes a restful sleep.

CELLIANT Viscose was developed by Hologenix®, creators of CELLIANT, a textile-based infrared ingredient brand, and Kelheim Fibres, a leading manufacturer of viscose specialty fibers. CELLIANT Viscose features natural minerals embedded into plant-based fibers and is biodegradable. It provides all the benefits of being a viscose fiber — lightweight, soft, highly breathable, excellent moisture management — as well as the fiber enhancements from CELLIANT infrared technology. In addition, CELLIANT is durable and will not wash out.

• Formula 1 cars will be cheaper in future

Carbon is the stuff Formula 1 cars are made of, at least the bodywork. But until now, carbon has been expensive. It can be produced more cheaply and efficiently if artificial intelligence monitors the production processes. A camera system combined with artificial intelligence automatically detects defects in the production of carbon fibres. This makes expensive manual inspection of the carbon fibres obsolete and the production price of the carbon fibre can be reduced in the long term.

For this idea, the young engineer Deniz Sinan Yesilyurt received the second prize of the "Digitalisation in Mechanical Engineering" Young Talent Award on 6 December.

Carbon fibres are sought after because of their good properties. They are very light - they weigh up to 50 percent less than aluminium. The combination of low weight and good mechanical properties offers many advantages. Especially in times of the energy transition, lightweight materials like carbon are more relevant than ever before. At the same time, carbon fibres are as resistant to external stresses as metals. However, achieving these good properties of carbon fibres is very complex.

Up to 300 individual fibre strands - bundles of individual fibres - have to be monitored simultaneously during production. If carbon fibres tear, it costs time and money to sort out the damaged fibres. This is just one example of various defects that can occur in the fibres during production.

Therefore, Deniz Sinan Yesilyurt attached a camera to the carbon fibre line that takes pictures of various fibre defects during production and collects them in a database. The artificial intelligence in the camera's information technology system evaluates the fibre defects by assigning the images to predefined reference defects. In doing so, it recognises various fibre defects with a classification accuracy of 99 per cent. The process can also be used in other areas that produce chemical fibres.

Deniz Sinan Yesilyurt received the prize from the German Engineering Federation (VDMA) in Frankfurt am Main, Germany. He is a Bachelor's graduate at the Institut für Textiltechnik (ITA) of RWTH Aachen University. The full title of his bachelor's thesis is: "Development of a Kl-supported process monitoring using machine learning to detect fibre damage in the stabilisation process". The VDMA awarded the prize to a total of four theses from different universities. The prize is awarded for outstanding theses and was offered in Germany, Austria and Switzerland.

Indorama Ventures Public Company Limited (IVL) has signed an ESG-Linked Revolving Credit Facility of €275 million with six syndicate banks, a further boost to the company’s long-standing commitment to sustainability-led corporate financing.

Tied to IVL’s ESG risk rating, the revolving credit facility’s pricing mechanism results in margin adjustments related to management score improvements across the Material ESG Issues as defined by independent sustainability and corporate governance research firms. The facility is available to IVL subsidiaries in Europe for two-years with the option to extend for one more year.

The facility is part of IVL’s corporate financing strategy across a range of instruments linked to the company’s ESG and sustainability commitments. In November 2021, the company issued a THB 10 billion triple-tranche Sustainability-Linked Bond (SLB), the largest SLB issued in Thailand. IVL is on track to achieve its 2025 ESG goals. More ambitious 2030 targets include a 30% reduction in Scope 1 & 2 combined greenhouse gas (GHG) intensity, 15% reduction in energy intensity, 25% use of renewable electricity, 20% reduction in water intensity, 90% diversion of waste from landfill, recycle 1.5 million tons in PET bale input annually.